About VisionatorMCP
VisionatorMCP is an MCP server in the Agents category: an MCP server for agents that enables models without vision/multimodal support to analyze images using local Ollama vision models.
Install
From source
git clone https://github.com/Tyrannmisu/VisionatorMCPThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
vision_analyze**analyze** (default): QA-focused screenshot analysis · **ask**: free-form prompt · **describe**: area-focused · **detect**: structured issue scan
Parameters not published.
vision_color**palette** (default): dominant color extraction · **match**: percentage of pixels in custom color ranges
Parameters not published.
vision_compareCompare two screenshots — pixel-level diff + VLM semantic analysis
Parameters not published.
vision_healthVerify Ollama connection, list available models, check config
Parameters not published.
vision_read_imageRead a local image file and convert to base64 (convenience helper)
Parameters not published.
vision_text**extract** (default): OCR text extraction (VLM or Tesseract) · **find**: locate specific text with bounding boxes
Parameters not published.
vision_validateCheck if an object/element is present. Optional `area` param to crop to a 3×2 grid region first.
Parameters not published.
Ask AI
✦
Ask AI about VisionatorMCP
Powered by Claude · Grounded in docs
I know everything about VisionatorMCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.